DMCA
Real-time texture synthesis by patch-based sampling (2001)
| Venue: | ACM Transactions on Graphics |
| Citations: | 173 - 12 self |
BibTeX
@ARTICLE{Liang01real-timetexture,
author = {Lin Liang and Ce Liu and Yingqing Xu and Baining Guo and Heung-yeung Shum},
title = {Real-time texture synthesis by patch-based sampling},
journal = {ACM Transactions on Graphics},
year = {2001},
volume = {20},
pages = {127--150}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We present a patch-based sampling algorithm for synthesizing textures from an input sample texture. The patch-based sampling algorithm is fast. Using patches of the sample texture as building blocks for texture synthesis, this algorithm makes high-quality texture synthesis a real-time process. For generating textures of the same size and comparable (or better) quality, patch-based sampling is orders of magnitude faster than existing texture synthesis algorithms. The patch-based sampling algorithm synthesizes high-quality textures for a wide variety of textures ranging from regular to stochastic. By sampling patches according to a non-parametric estimation of the local conditional MRF density, we avoid mismatching features across patch boundaries. Moreover, the patch-based sampling algorithm remains effective when pixel-based non-parametric sampling algorithms fail to produce good results. For natural textures, the results of the patch-based sampling look subjectively better.
Keyphrases
patch-based sampling algorithm patch-based sampling real-time texture synthesis high-quality texture real-time process input sample texture wide variety good result sample texture patch boundary pixel-based non-parametric sampling algorithm natural texture patch-based sampling look texture synthesis algorithm non-parametric estimation texture synthesis local conditional mrf density building block
